© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88834
    Prev
    Next
    INDEX
    Explanations

    terminal commands and execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ş
    0.25
     underm
    0.24
    setRoot
    0.24
     cannibal
    0.23
     exquisite
    0.23
    Ш
    0.23
     enfermed
    0.23
     incompar
    0.22
     gangster
    0.22
     gastronomic
    0.22
    POSITIVE LOGITS
     savent
    0.27
     Ears
    0.26
     tarko
    0.26
     प्रकार
    0.26
     Deutschland
    0.26
     ماشینونه
    0.26
     ////
    0.26
    炡
    0.25
    ENU
    0.25
     Encoding
    0.24
    Activations Density 0.001%

    No Known Activations